© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135014
    Prev
    Next
    INDEX
    Explanations

    break open

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    H
    1.83
    W
    1.74
    Y
    1.63
    F
    1.61
    V
    1.61
    and
    1.48
    T
    1.48
    S
    1.45
    ad
    1.45
    P
    1.43
    POSITIVE LOGITS
     molécules
    0.95
    т
    0.94
     dets
    0.89
     vacuoles
    0.89
     conglomerates
    0.89
     massac
    0.88
     synergies
    0.86
     Antennes
    0.85
     véhicules
    0.85
     vatt
    0.84
    Activations Density 0.000%

    No Known Activations